论文标题
在不连续的情况下，基弗 - 沃尔夫维茨算法的融合
Convergence of the Kiefer-Wolfowitz algorithm in the presence of discontinuities
论文作者
论文摘要
在本文中，我们估计了随机近似算法的预期误差，其中使用该函数的随机表示的有限差异发现了函数的最大值。使用合适的参数实现$ o（n^{ - 1/5}）$的$ O（n^{ - 1/5}）$的错误估计。相对于以前的研究的新颖性是，我们允许随机表示不连续，并由可能依赖的随机变量（满足混合条件）组成。
In this paper we estimate the expected error of a stochastic approximation algorithm where the maximum of a function is found using finite differences of a stochastic representation of that function. An error estimate of $O(n^{-1/5})$ for the $n$th iteration is achieved using suitable parameters. The novelty with respect to previous studies is that we allow the stochastic representation to be discontinuous and to consist of possibly dependent random variables (satisfying a mixing condition).
